Awesome Source-free Test-time Adaptation   [](https://github.com/sindresorhus/awesome) [](https://GitHub.com/Naereen/StrapDown.js/graphs/commit-activity)

• Methods

  • Decorate the Newcomers: Visual Domain Prompt for Continual Test Time Adaptation
  • Semantic Photo Manipulation with a Generative Image Prior
  • Model Adaptation: Unsupervised Domain Adaptation without Source Data
  • Test-Time Training with Self-Supervision for Generalization under Distribution Shifts
  • TTT++: When Does Self-Supervised Test-Time Training Fail or Thrive? - epfl/ttt-plus-plus)
  • Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Data
  • Test-Time Training with Masked Autoencoders
  • Improved Test-Time Adaptation for Domain Generalization
  • PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization
  • Contrastive Test-Time Adaptation
  • Divide and Contrast: Source-free Domain Adaptation via Adaptive Contrastive Learning
  • Tent: Fully Test-Time Adaptation by Entropy Minimization
  • Uncertainty Reduction for Model Adaptation in Semantic Segmentation - uncertainty-for-adaptation)
  • Bayesian Adaptation for Covariate Shift
  • MATE: Masked Autoencoders are Online 3D Test-Time Learners
  • On the Robustness of Open-World Test-Time Training: Self-Training with Dynamic Prototype Expansion - Li/OWTTT)
  • Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation - learn/SHOT)
  • Improving robustness against common corruptions by covariate shift adaptation
  • Efficient Test-Time Model Adaptation without Forgetting - eggplant/EATA)
  • Confidence Score for Source-Free Unsupervised Domain Adaptation - JMDS)
  • Towards Stable Test-time Adaptation in Dynamic Wild World - eggplant/SAR)
  • - burns/feature-alignment)
  • TTN: A Domain-Shift Aware Batch Normalization in Test-Time Adaptation
  • Delta: Degradation-Free Fully Test-Time Adaptation
  • Generative Pseudo-label Refinement for Unsupervised Domain Adaptation
  • A Free Lunch for Unsupervised Domain Adaptive Object Detection without Source Data
  • Adapting ImageNet-scale models to complex distribution shifts with self-learning
  • Continual Test-Time Domain Adaptation
  • Revisiting Realistic Test-Time Training: Sequential Inference and Adaptation by Anchored Clustering - Lab-SCUT/TTAC)
  • Attracting and Dispersing: A Simple Approach for Source-free Domain Adaptation
  • Adaptive Adversarial Network for Source-Free Domain Adaptation
  • Test-Time Adaptation via Conjugate Pseudo-labels
  • Towards Understanding GD with Hard and Conjugate Pseudo-labels for Test-Time Adaptation
  • TeSLA: Test-Time Self-Learning With Automatic Adversarial Augmentation
  • Test-Time Classifier Adjustment Module for Model-Agnostic Domain Generalization
  • Invariance Through Latent Alignment - through-latent-alignment.github.io/)
  • Source-Free Domain Adaptation via Distribution Estimation
  • ActMAD: Activation Matching to Align Distributions for Test-Time-Training
  • Robustness to corruption in pre-trained Bayesian neural networks
  • TTT++: When Does Self-Supervised Test-Time Training Fail or Thrive? - epfl/ttt-plus-plus)
  • Source-Free Adaptation to Measurement Shift via Bottom-Up Feature Restoration
  • MEMO: Test Time Robustness via Adaptation and Augmentation
  • Test time Adaptation through Perturbation Robustness - WS'21
  • Domain Impression: A Source Data Free Domain Adaptation Method
  • Back to the Source: Diffusion-Driven Test-Time Adaptation
  • Generalized Source-free Domain Adaptation - SFDA)
  • Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptation
  • Test-Time Adaptation via Self-Training with Nearest Neighbor Information
  • Extrapolative Continuous-time Bayesian Neural Network for Fast Training-free Test-time Adaptation
  • Balancing Discriminability and Transferability for Source-Free Domain Adaptation - sfda)
  • Test-Time Fast Adaptation for Dynamic Scene Deblurring via Meta-Auxiliary Learning
  • Adaptive Risk Minimization: Learning to Adapt to Domain Shift - risk-minimization)
  • Learning to Generalize across Domains on Single Test Samples - ICLR2022)
  • Meta-DMoE: Adapting to Domain Shift by Meta-Distillation from Mixture-of-Experts - DMoE)
  • NOTE: Robust Continual Test-time Adaptation Against Temporal Correlation
  • Decorate the Newcomers: Visual Domain Prompt for Continual Test Time Adaptation
  • Robust Test-Time Adaptation in Dynamic Scenarios - DA/RoTTA)
  • A Probabilistic Framework for Lifelong Test-Time Adaptation
  • EcoTTA: Memory-Efficient Continual Test-time Adaptation via Self-distilled Regularization
  • Domain Adaptation in the Absence of Source Domain Data
  • Semantic Photo Manipulation with a Generative Image Prior
  • Collaborative Sampling in Generative Adversarial Networks - epfl/collaborative-gan-sampling)
  • Universal Source-Free Domain Adaptation - cvpr2020)
  • Adaptive Methods for Real-World Domain Generalization
  • Robust Mean Teacher for Continual and Gradual Test-Time Adaptation - time-adaptation)
  • MECTA: Memory-Economic Continual Test-Time Model Adaptation
  • Neuro-Modulated Hebbian Learning for Fully Test-Time Adaptation
  • Parameter-free Online Test-time Adaptation
  • Evaluating the Adversarial Robustness of Adaptive Test-time Defenses
  • Test-time Adaptation in the Dynamic World with Compound Domain Knowledge Management - L'23

• Applications

  • Fully Test-Time Adaptation for Image Segmentation
  • Fully Test-Time Adaptation for Image Segmentation
  • Fully Test-Time Adaptation for Image Segmentation
  • Fully Test-Time Adaptation for Image Segmentation
  • Fully Test-Time Adaptation for Image Segmentation
  • Fully Test-Time Adaptation for Image Segmentation
  • Fully Test-Time Adaptation for Image Segmentation
  • Fully Test-Time Adaptation for Image Segmentation
  • Fully Test-Time Adaptation for Image Segmentation
  • Fully Test-Time Adaptation for Image Segmentation
  • Fully Test-Time Adaptation for Image Segmentation
  • Fully Test-Time Adaptation for Image Segmentation
  • Fully Test-Time Adaptation for Image Segmentation
  • Fully Test-Time Adaptation for Image Segmentation
  • Source-Free Domain Adaptation for Image Segmentation - b/SFDA)
  • Fully Test-Time Adaptation for Image Segmentation
  • Fully Test-Time Adaptation for Image Segmentation
  • Fully Test-Time Adaptation for Image Segmentation
  • SS-SFDA: Self-Supervised Source-Free Domain Adaptation for Road Segmentation in Hazardous Environments
  • Consistent Video Depth Estimation - Video-Depth-Estimation/)
  • Fully Test-Time Adaptation for Image Segmentation
  • Adapting Off-the-Shelf Source Segmenter for Target Medical Image Segmentation
  • Source-Free Domain Adaptation for Semantic Segmentation
  • Self-Supervised Policy Adaptation during Deployment
  • Source-Free Domain Adaptation for Image Segmentation - b/SFDA)
  • Towards Robust and Adaptive Motion Forecasting: A Causal Representation Perspective - epfl/causalmotion)
  • Test-Time Personalization with a Transformer for Human Pose Estimation
  • On the Road to Online Adaptation for Semantic Image Segmentation
  • Test-Time Training Can Close the Natural Distribution Shift Performance Gap in Deep Learning Based Compressed Sensing - lab/ttt_for_deep_learning_cs)
  • Source-free Video Domain Adaptation by Learning Temporal Consistency for Action Recognition
  • Ev-TTA: Test-Time Adaptation for Event-Based Object Recognition
  • MM-TTA: Multi-Modal Test-Time Adaptation for 3D Semantic Segmentation - labs.com/~mas/MM-TTA/)
  • Source-Free Object Detection by Learning to Overlook Domain Style - Free-Object-Detection-by-Learning-to-Overlook-Domain-Style)
  • Video Test-Time Adaptation for Action Recognition - at.github.io/vitta)
  • AuxAdapt: Stable and Efficient Test-Time Adaptation for Temporally Consistent Video Semantic Segmentation
  • Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models
  • TTA-COPE: Test-Time Adaptation for Category-Level Object Pose Estimation - lee/ttacope)
  • SfM-TTR: Using Structure from Motion for Test-Time Refinement of Single-View Depth Networks - TTR)
  • Fully Test-Time Adaptation for Image Segmentation
  • Fully Test-Time Adaptation for Image Segmentation
  • Fully Test-Time Adaptation for Image Segmentation
  • Fully Test-Time Adaptation for Image Segmentation
  • Fully Test-Time Adaptation for Image Segmentation
  • Fully Test-Time Adaptation for Image Segmentation
  • Fully Test-Time Adaptation for Image Segmentation
  • Fully Test-Time Adaptation for Image Segmentation
  • Fully Test-Time Adaptation for Image Segmentation

• Benchmark

  • On Pitfalls of Test-Time Adaptation - lab/ttab)
  • On Pitfalls of Test-Time Adaptation - lab/ttab)